Fault Tolerant Resource Management Scheme for Computational Grids

Abstract

With the fast expansion in wide area networks leading to availability of low cost fundamental computational resources, the popularity of computational grids has increased. Effective dynamic load balancing (DLB), scheduling and fault tolerance collectively determine the QoS requirements of users from computational grids. In an effort to enhance the previously proposed and implemented DLB algorithms for hierarchical and distributed computational grids viz. DLBCGBH – H / G, Fuzzy Min-Max Scheduling (FMiMaS) was proposed and integrated with the Local scheduling proposed in DLBCGBH – H / D, to result into two resource management schemes viz. Fuzzy Hierarchical & Fuzzy Distributed approaches, based on hybrid scheduling demonstrating tremendous improvements against the performance metrics viz. Average Consumed Time, Average Waiting Time and Number of Tasks Migrated. In this paper, these two approaches are tested for fault tolerance against various possibilities of node failure to assess their robustness for the domain of computational grids.